Skip to main content
skill CX Codex

music-generation · bytedance — Claude Code skill: AI song generation

music-generation turns a style and mood description into a finished track through the MiniMax music API, with sung lyrics or as a pure instrumental.

MIT 314 installs ★ 85,586 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add bytedance/deer-flow --skill music-generation -a claude-code
Open on GitHub

What music-generation does

The skill builds a song from a JSON spec containing title, a prompt describing style, mood and scene, and an optional lyrics field, then runs scripts/generate.py pointing at that spec and an output MP3 path. Leave lyrics out and the model writes its own words from the prompt; set is_instrumental: true and it skips vocals entirely.

Lyrics for non-English songs go straight into the lyrics field in the target language, using structure markers like [Verse] and [Chorus]. Once rendered, the agent hands the file back through present_files and offers to tweak the style or words.

The script needs MINIMAX_API_KEY set as an environment variable to reach the API; it defaults to the music-2.6-free model, with MINIMAX_MUSIC_MODEL=music-2.6 available for paid-tier limits.

What it helps with

  • score background music for a scene or mood
  • draft a jingle or theme tune for a project
  • render an instrumental track with no vocals
  • set existing lyrics to music in a chosen style
  • produce a song in a specific language from a text prompt

Example prompts for the agent

  • Write a melancholic indie folk track about a rainy night at a cafe
  • Generate an instrumental background track in a light jazz style
  • Turn these lyrics into a pop ballad

How to install music-generation

1Skills CLI (Vercel)

npx skills add bytedance/deer-flow --skill music-generation -a claude-code

2Manually: put the files in place

~/.claude/skills/music-generation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/music-generation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about music-generation

How do I install music-generation in Claude Code?

Run npx skills add bytedance/deer-flow --skill music-generation -a claude-code; the skill lands at ~/.claude/skills/music-generation/SKILL.md.

What does music-generation do?

It packages a style, mood and optional lyrics into a JSON spec, feeds that to generate.py, which calls the MiniMax music API and returns an MP3 of the generated song.

What does music-generation require to work?

It needs a MINIMAX_API_KEY environment variable; the model defaults to music-2.6-free, with music-2.6 available for paid-tier users wanting higher limits.

Source text

SKILL.md · MIT
---
name: music-generation
description: Use this skill when the user requests to generate, create, compose, or produce music or songs — background music, theme songs, jingles, or instrumental tracks. Generates a song from a style/mood prompt and optional lyrics via the MiniMax music API.
---

# Music Generation Skill

## Overview

This skill generates songs (vocal or instrumental) from a structured JSON spec using the
MiniMax music generation API (`/v1/music_generation`). You describe the style/mood/scene in
`prompt`, optionally provide `lyrics`, and the script returns an MP3.

## Workflow

### Step 1: Understand Requirements

Identify the desired style, mood, scene, language, and whether the user wants vocals or a
pure instrumental track. Decide whether to supply lyrics or let the model write them.

### Step 2: Create the Spec JSON

Write a JSON file in `/mnt/user-data/workspace/` named `{descriptive-name}.json`:

```json
{
  "title": "Rainy Night Cafe",
  "prompt": "indie folk, melancholic, introspective, walking alone, cafe",
  "lyrics": "[verse]\nStreetlights glow the night wind sighs\n[chorus]\nPush the wooden door warm air inside"
}
```

Fields:
- `title` (optional): a human-readable name.
- `prompt` (required): style, mood, and scene. Drives the musical character.
- `lyrics` (optional): song lyrics. Use `\n` between lines and structure tags such as
  `[Intro]`, `[Verse]`, `[Pre Chorus]`, `[Chorus]`, `[Bridge]`, `[Outro]`.
- `is_instrumental` (optional, bool): set `true` for a pure instrumental track (no lyrics needed).

Behavior:
- `lyrics` provided → those lyrics are sung.
- `is_instrumental: true` → instrumental, no vocals.
- neither → the model auto-writes lyrics from `prompt` (`lyrics_optimizer`).

### Step 3: Execute Generation

```bash
python /mnt/skills/public/music-generation/scripts/generate.py \
  --prompt-file /mnt/user-data/workspace/rainy-night-cafe.json \
  --output-file /mnt/user-data/outputs/rainy-night-cafe.mp3
```

Parameters:
- `--prompt-file`: Absolute path to the JSON spec (required).
- `--output-file`: Absolute path for the output MP3 (required).

[!NOTE]
Do NOT read the python file, just call it with the parameters.

## Environment

- `MINIMAX_API_KEY` (required): your MiniMax interface key.
- `MINIMAX_API_HOST` (optional): default `https://api.minimaxi.com`.
- `MINIMAX_MUSIC_MODEL` (optional): default `music-2.6-free` (works for all API-key users);
  paid/Token-Plan users can set `music-2.6` for higher limits.

## Output Handling

- Music is saved as MP3 (typically in `/mnt/user-data/outputs/`).
- Returned audio must decode to nonempty bytes and have an ID3 tag header or MPEG frame signature. This is a header sanity check, not complete audio decoding.
- Malformed, empty or unrecognized audio is rejected before creating the output directory or opening the output file; an existing output is preserved.
- Missing audio reports "MiniMax returned no audio data"; whitespace-only hex reports "MiniMax audio decoded to empty bytes".
- Share the generated file with the user using the present_files tool.
- Offer to iterate on style or lyrics if adjustments are needed.

## Notes

- Keep `prompt` focused on style/mood/scene; put the actual sung words in `lyrics`.
- For non-English songs, write `lyrics` in the target language.

© bytedance · MIT · bytedance/deer-flow

Similar skills

All skills for AI and ML →

music-generation by other authors comes first.

From the same set19

The whole set →
systematic-literature-review The systematic-literature-review Claude Code skill synthesizes findings across academic papers on a topic. It searches arXiv and produces a cited report or annotated bibliography. CX Codex +1 2,500installs podcast-generation podcast-generation turns articles, reports, or documentation into a two-host conversational podcast and produces an MP3 with an optional transcript. CX Codex +1 2,400installs surprise-me The surprise-me skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode discovers enabled skills and turns them into one unexpected result. It reacts to requests for a surprise, inspiration, or something interesting. CX Codex +1 2,300installs vercel-deploy The vercel-deploy skill tarballs your project, picks the framework on its own and pushes it to Vercel. You get a preview link plus a claim link for moving the deploy into your account. CX Codex +1 2,200installs code-documentation The code-documentation skill auto-generates README files, API references, architecture docs, and developer guides straight from your codebase. Use it to document projects, libraries, and APIs without manual effort. CX Codex +1 2,000installs newsletter-generation newsletter-generation generates professional email digests and newsletters with topic research via web search, multi-source curation, and ready-to-publish markdown output. CX Codex +1 1,900installs bootstrap bootstrap — a skill for Claude Code, Codex, Cursor, and other platforms. Generates a tailored SOUL.md file through an adaptive onboarding chat to define your AI companion's identity. CX Codex +1 1,600installs skill-reviewer skill-reviewer is a Claude Code skill that checks existing skill packages for readiness, trigger behavior, safety boundaries, and supporting evidence. It runs on requests to audit or grade a skill. CX Codex +1 207installs

Project sponsors

Companies that keep this analytics open